List your company

Post-shift accepted-trajectory risk estimation on Multi-seed RAG tool mean

0.5Risk Estimation (Post-shift Accepted Trajectory)ToolChain-CRC
0.1122.7315.357.969Jun 16, 2026

Evaluation results

MethodLinks
ToolChain-CRCCalibration Strategy=Trajectory calibration2026.060.5
Fixed trajectoryCalibration Strategy=Fixed trajectory2026.060.6
Prompt/retrieval-onlyCalibration Strategy=Prompt/retrieval-only2026.065.1
Final-onlyCalibration Strategy=Final-answer-only2026.0610.2